sam announces built-in support for decision models in Discourse AI, a technology originally developed by TypeSafe.ai and adopted by providers like CloudFlare and OpenAI. These models allow users to classify text and images by answering arbitrary questions, offering superior speed, accuracy, and cost-efficiency compared to standard language models. This feature is currently accessible via the “Classify” node within Discourse Workflows, enabling use cases such as automatic moderation, team notifications, and dynamic tagging.
satonotdead expresses enthusiasm for using decision models for response triage and proposes integrating them into common agents to create “Senior Helpers” that classify inputs before delegating tasks. In response, sam confirms interest in exploring decision models as a gate to route queries to specific subagents.
satonotdead details a proposed workflow where a gate setting points to a decision model that selects from existing subagent descriptions (e.g., for public writing, links, web updates, or archives). The system would only offer subagents accessible to the current user. If the classification confidence exceeds a threshold, the subagent runs directly; otherwise, the result serves as a hint for the parent LLM. Additionally, this mechanism could function as a guard for safety rules, such as automatically rejecting requests for investment advice without relying on prompt engineering, which can drift under pressure.
I am very happy to announce we now have built-in support for decision models.
Decision models were championed and first developed by TypeSafe.ai and since then have been implemented by numerous providers including CloudFlare (clef), Open AI (decisions api) and many more.
They allow you to classify text and images by answering arbitrary questions about the inputs quickly, accurately and cheaply.
The new intelligence can be used for a very large amount of workflows given it allows you to classify text (and images) using your own designed classifier.
Automatic moderation - get notified when discussions get heated
Notify particular team members when particular topics are discussed
Automatic tagging and categorization
And much more
Enjoy, and please share interesting workflows you come up with.
I find this great for response triage agents; I’m already in my first tests to see how it goes. I understand that these new models for decision-making are very precise and fast, and I’m glad we can have them in Discourse.
I wonder if there are plans and/or if it is technically possible to incorporate them into common agents as well, to develop ‘Senior Helpers’ that first classify before delegating. Or does that not make sense at all?
It’s likely that I haven’t yet fully understood their real best use case, and maybe I’m asking something out of place.
I think there are a large number of uses here, using them as a gate that finds the right agent or subagent to answer is certainly something I want to explore
a chart a member shares, reviewed against our public method
Today the parent LLM reads the subagent descriptions and picks one with spawn_agent. The gate would take that decision from it:
A gate setting on the agent, pointing to a decision model.
The choices are the subagent descriptions that already exist, plus “answer yourself”. Nothing new for admins to write.
Only the subagents the current user can access are offered.
Above a confidence threshold, the subagent runs directly. Below it, the result reaches the parent LLM as a hint and the LLM decides, as it does now.
Since decision models classify images, “member shared a chart” comes from the image itself.
The same gate, as a yes/no question, would also work as a guard before the LLM runs.
We’re an education community and we don’t give signals, price targets or investment advice, so “is this asking for a trading signal?” → fixed reply. Today that rule is a line in every prompt, and models drift from it under pressure.
If you get to it, we’d be glad to try an early version on our forum.
